LEARNet: A Learning Entropy-Aware Representation Network for Educational Video Understanding
Open Access
Abstract
Educational videos contain long periods of visual redundancy, where only a few frames convey meaningful instructional information. Conventional video models, which are designed for dynamic scenes, often fail to capture these subtle pedagogical transitions. We introduce LEARNet, an entropy-aware framework that models educational video understanding as the extraction of high-information instructional content from low-entropy visual streams. LEARNet combines a Temporal Information Bottleneck (TIB) for selecting pedagogically significant keyframes with a Spatial–Semantic Decoder (SSD) that produces fine-grained annotations refined through a proposed Relational Consistency Verification Network (RCVN). This architecture enables the construction of EVUD-2M, a large-scale benchmark with multi-level semantic labels for diverse instructional formats. LEARNet achieves substantial redundancy reduction (70.2%) while maintaining high annotation fidelity (F1 = 0.89, mAP@50 = 0.88). Grounded in information-theoretic principles, LEARNet provides a scalable foundation for tasks such as lecture indexing, visual content summarization, and multimodal learning analytics.Keywords
This publication has 53 references indexed in Scilit:
- A generalized fault diagnosis framework for rotating machinery based on phase entropyReliability Engineering & System Safety, 2024
- Key Frame Extraction from Videos Based on SIFT and Structural Similarity2023
- Simple Open-Vocabulary Object Detection2022
- Improving Image Description with Auxiliary Modality for Visual Localization in Challenging ConditionsInternational Journal of Computer Vision, 2020
- Convolutions and Convolutional Neural Networks2020
- A Diagram is Worth a Dozen Images2016
- Duckduckgo http://www.duckduckgo.com or http://www.ddg.ggTechnical Services Quarterly, 2012
- VSUMM: A mechanism designed to produce static video summaries and a novel evaluation methodPattern Recognition Letters, 2011
- Video shot boundary detection: Seven years of TRECVid activityComputer Vision and Image Understanding, 2010
- Temporal video segmentation: A surveySignal Processing: Image Communication, 2001